Kimi K3.1 Pro scores 9.9% on agentic WeirdML v3, ahead of Kimi-K3 but behind Claude Haiku 5.5
scaling01 · x · 2026-11-06
htihle ran Kimi K3.1 Pro via Kimi Code (Fireworks provider) on WeirdML v3, a fully agentic benchmark with 11 complex hand-made tasks where models must explore unfamiliar data and build ML pipelines under unspecified goals and limited feedback.
K3.1 Pro scored 9.9%, ahead of Kimi-K3 at 7.5% but well behind top models like Claude Haiku 5.5. The leaderboard shows GPT-6 Astra, GPT-6.1 Sol and Claude Opus 5.5 leading, with K3.1 Pro ranked 14th.
More from Models
- Grok Bot users rage as weekly limits silently slashed, $300/mo SuperGrok Heavy customers cancel — steipete · 2026-11-06
- Researcher: Opus over-refuses simple safety-topic questions, even on existing writeups — DimitrisPapail · 2026-11-06
- Apple's GSM-Symbolic paper: renaming numbers sinks SOTA models' math scores — imjustnewatai · 2026-11-06
- Oc-e-Non-v1: a tersified Qwen3-4B that cuts response length by 50%, built with Heretic — -p-e-w- · 2026-11-06
- Robot RSI: testing whether frontier models can set up robot environments — qinzytech · 2026-11-06
- NetEase Youdao's Confucius4-R2T2: Streaming ASR That Never Rewrites Its Output — dr_cintas · 2026-11-06